Digital holographic imaging systems are promising as they provide 3-D information of the object. However, theacquisition of holograms during experiments can be adversely affected by the speckle noise in coherent digital holographicsystems. Several different denoising algorithms have been proposed. Traditional denoising algorithms average severalholograms under different experimental conditions or use conventional filters to remove the speckle noise. However, thesetraditional methods require complex holographic experimental conditions. Besides time-consuming, the use of traditionalneural networks has been difficult to extract speckle noise characteristics from holograms and the resulting holographicreconstructions have not been ideal. To address tradeoff between speckle noise reduction and efficiency, we analyzeholograms in the spectrum domain for fast speckle noise reduction, which can remove multiple-levels speckle noise basedon convolutional neural networks using only a single hologram. In order to effectively reduce the speckle noise associatedwith the hologram, the data set of the neural network training cannot use the current popular image data set. To achievepowerful noise reduction performance, neural networks use multiple-level speckle noise data sets for training. In contrastto existing traditional denoising algorithms, we use convolutional neural networks in spectral denoising for digitalhologram. The proposed technique enjoys several desirable properties, including (i) the use of only a single hologram toefficiently handle various speckle noise levels, and (ii) faster speed than traditional approaches without sacrificingdenoising performance. Experimental results and holographic reconstruction demonstrate the efficiency of our proposedneural network.
展开▼
